Cognee × AmbactiBring Cognee into
the flow of work.
A little less busywork with Cognee.
Add Data1 capabilities+
- Add data to cognee datasets
Add text_data to a Cognee dataset to "cognify" later in the Cognee memory engine
Cognify2 capabilities+
- Cognify an existing dataset into memory
After adding text data to a Cognee dataset, trigger cognify to build a knowledge graph based memory from it
- Enrich an existing dataset graph with memify
Run Cognee enrichment tasks over an existing dataset graph (or over custom data with custom extraction/enrichment tasks)
Search1 capabilities+
- Search in cognee memory
Run a search query in Cognee memory engine
Delete2 capabilities+
- Delete a dataset by its ID
Permanently delete a dataset and all its associated data
- Delete a specific data item from a dataset
Remove a specific data item from a dataset while keeping the dataset intact
Skill8 capabilities+
- Apply an approved skill improvement proposal
Apply a previously created proposal to the skill (writes the new procedure)
- Delete a skill from a dataset
Delete one skill (graph node and embeddings) from a dataset
- Get many skills
List the skills ingested into a dataset
- Get a skill improvement proposal
Fetch a proposal with its before/after procedures, rationale and confidence
- Get a skill including its procedure body
Fetch one skill (including its full procedure) by ID
- Ingest a skill md into a dataset
Ingest inline SKILL.md markdown as a dataset-scoped skill (no file upload)
- Propose a skill improvement from a weak run
Record a low-scoring skill run and create a skill-improvement proposal (not applied)
- Run a skill aware agentic review
Run an AGENTIC_COMPLETION search that loads the given skill to review a task
Memory5 capabilities+
- Forget data from cognee memory
Delete a dataset, a single data item, or everything you own. Optionally clear only the graph and vector memory while keeping raw files.
- Recall information from cognee memory
Query memory with any Cognee search type, optionally combining knowledge-graph hits with session Q&A and trace entries
- Remember text or a file in cognee memory
Ingest text or a binary file into a dataset and build the knowledge graph in one call (add + cognify)
- Store a session qa trace or feedback entry
Store a typed session memory entry: a question/answer turn, an agent trace step, or feedback on an earlier answer
- Replace a remembered data item
Replace an existing data item with new text or a file; the old version is deleted and the new one is ingested into the graph
Dataset5 capabilities+
- Create a dataset
Create a dataset by name (returns the existing one if the name is already taken)
- Get the data items of a dataset
List the documents/files stored in a dataset, including their UUIDs for Forget, Update and Delete Data
- Get many datasets
List the datasets you have access to
- Get dataset processing progress
Pipeline status together with in-flight progress (files completed / total, current stage), one item per dataset
- Get dataset processing status
Pipeline status per dataset (pending, running, completed, failed). Use it to poll after Run in Background.
Session2 capabilities+
- Get a session
Get one session with its Q&A and trace entries, usage and cost
- Get many sessions
List sessions with activity, status and cost, newest first
Frequently asked
questions.
What could an Ambacti integration do with Cognee?
The documented operations include Add Data: Add data to cognee datasets; Cognify: Cognify an existing dataset into memory; Cognify: Enrich an existing dataset graph with memify; Search: Search in cognee memory.
Could I keep a workflow read-only?
For a read-only workflow, limit account permissions to reading data and exclude actions that create, update, or delete records.
Will every action run automatically?
Choose which steps could run on their own and which should pause for review. Changes should follow the permissions and approval rules you set.
Do I need to review actions in Cognee?
Decide which work could run on its own and which steps need your review.